Image-Based Differentiation of Bacterial and Fungal Keratitis Using Deep Convolutional Neural Networks.
Image-Based Differentiation of Bacterial and Fungal Keratitis Using Deep Convolutional Neural Networks.
复制标题
DOI：
10.1016/j.xops.2022.100119
复制
发表时间：
2022-06
影响因子：
--
通讯作者：
Song X
中科院分区：
文献类型：
--
作者：
Redd TK;Prajna NV;Srinivasan M;Lalitha P;Krishnan T;Rajaraman R;Venugopal A;Acharya N;Seitzman GD;Lietman TM;Keenan JD;Campbell JP;Song X
开发基于图像的细菌和真菌角膜溃疡的计算机视觉模型，并将其性能与人类专家进行比较。诊断性能的横断面比较。来自印度南部4个中心的急性细菌性或真菌性角膜炎患者。五个卷积神经网络(CNN)使用从手持摄像机收集的图像进行训练，这些图像来自印度南部经培养证实的角膜溃疡患者，这些患者是在2006年至2015年进行的临床试验中招募的。他们的表现在来自南印度的2个坚持测试集(1个单中心和1个多中心)上进行了评估。12名当地角膜专家对多中心测试集中的图像进行了远程解读，以便与CNN的表现进行直接比较。接收器工作特性曲线下面积(AUC)单独和每个组的集合(即，CNN集合和人类集合)。表现最好的CNN架构是MobileNet，它在单中心测试集(其他CNN范围为0.68-0.84)上的AUC为0.86，在多中心测试集(其他CNN范围为0.75-0.83)上的AUC为0.83。多中心测试集上的专家人类AUC范围从0.42到0.79。CNN组获得的AUC(0.84)显著高于人类组(0.76；P<；0.01)。CNN对真菌(81%)和细菌(75%)溃疡的准确率相对较高，而人类对细菌(88%)和真菌(56%)溃疡的准确率相对较高。表现最好的CNN和表现最好的人类的合奏获得了最高的AUC 0.87，尽管这在统计学上并没有显著高于最好的CNN(0.83；P=0.17)或最佳人类(0.79；P=0.09)。与角膜专家相比，计算机视觉模型在识别角膜溃疡的潜在感染原因方面取得了超乎人类的表现。表现最好的模型，MobileNet，在没有任何额外的临床或历史信息的情况下，获得了0.83到0.86的AUC。这些发现表明，未来有可能实施这些模型，以便能够在感染性角膜炎的治疗中更早地进行定向抗菌治疗，这可能会改善视觉结果。将临床病史和专家意见纳入预测模型的其他研究正在进行中。
Develop computer vision models for image-based differentiation of bacterial and fungal corneal ulcers and compare their performance against human experts. Cross-sectional comparison of diagnostic performance. Patients with acute, culture-proven bacterial or fungal keratitis from 4 centers in South India. Five convolutional neural networks (CNNs) were trained using images from handheld cameras collected from patients with culture-proven corneal ulcers in South India recruited as part of clinical trials conducted between 2006 and 2015. Their performance was evaluated on 2 hold-out test sets (1 single center and 1 multicenter) from South India. Twelve local expert cornea specialists performed remote interpretation of the images in the multicenter test set to enable direct comparison against CNN performance. Area under the receiver operating characteristic curve (AUC) individually and for each group collectively (i.e., CNN ensemble and human ensemble). The best-performing CNN architecture was MobileNet, which attained an AUC of 0.86 on the single-center test set (other CNNs range, 0.68–0.84) and 0.83 on the multicenter test set (other CNNs range, 0.75–0.83). Expert human AUCs on the multicenter test set ranged from 0.42 to 0.79. The CNN ensemble achieved a statistically significantly higher AUC (0.84) than the human ensemble (0.76; P < 0.01). CNNs showed relatively higher accuracy for fungal (81%) versus bacterial (75%) ulcers, whereas humans showed relatively higher accuracy for bacterial (88%) versus fungal (56%) ulcers. An ensemble of the best-performing CNN and best-performing human achieved the highest AUC of 0.87, although this was not statistically significantly higher than the best CNN (0.83; P = 0.17) or best human (0.79; P = 0.09). Computer vision models achieved superhuman performance in identifying the underlying infectious cause of corneal ulcers compared with cornea specialists. The best-performing model, MobileNet, attained an AUC of 0.83 to 0.86 without any additional clinical or historical information. These findings suggest the potential for future implementation of these models to enable earlier directed antimicrobial therapy in the management of infectious keratitis, which may improve visual outcomes. Additional studies are ongoing to incorporate clinical history and expert opinion into predictive models.
登录
查看更多内容
DOI：
10.3390/diagnostics11071246
发表时间：
2021-07-12
期刊：
Diagnostics (Basel, Switzerland)
影响因子：
--
作者：
Hung N;Shih AK;Lin C;Kuo MT;Hwang YS;Wu WC;Kuo CF;Kang EY;Hsiao CH
通讯作者：
Hsiao CH
影响因子：
4.1
作者：
Pascolini, Donatella;Mariotti, Silvio Paolo
通讯作者：
Mariotti, Silvio Paolo
影响因子：
8.1
作者：
Prajna, N. Venkatesh;Krishnan, Tiruvengada;Mascarenhas, Jeena;Rajaraman, Revathi;Prajna, Lalitha;Srinivasan, Muthiah;Raghavan, Anita;Oldenburg, Catherine E.;Ray, Kathryn J.;Zegans, Michael E.;McLeod, Stephen D.;Porco, Travis C.;Acharya, Nisha R.;Lietman, Thomas M.
通讯作者：
Lietman, Thomas M.
影响因子：
4.4
作者：
Dalmon, Cyril;Porco, Travis C.;Acharya, Nisha R.
通讯作者：
Acharya, Nisha R.
影响因子：
--
作者：
Jeng, Bennie H.;Gritz, David C.;Wong, Ira G.
通讯作者：
Wong, Ira G.